VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models

摘要

Vision-language models (VLMs) achieve strong performance on standard, high-quality datasets, but we still don't fully understand how they perform under real-world image distortions. We present **VLM-RobustBench**, a benchmark spanning 49 augmentation types across noise, blur, weather, digital, and geometric perturbations, evaluated under graded severities (low/mid/high) and binary transforms, yielding 133 corrupted settings. We evaluate VLMs from four families (Qwen, InternVL, Molmo, Gemma) on two complementary benchmarks: MMBench (visually grounded) and MMMU-Pro (reasoning-oriented). Our results reveal that visual severity is a weak predictor of difficulty: low-severity spatial perturbations often degrade performance more than visually severe photometric corruptions. In particular, low-severity *glass_blur* reduces MMBench accuracy by about 8pp on average across models, while the largest drops arise from resampling and geometric distortions (e.g., *upsample*, *elastic\_transform*, reaching up to 34pp. Overall, our findings suggest current VLMs are *semantically strong but spatially fragile*, motivating the definition of novel robustness evaluation protocols and training regimes that emphasize resampling and geometric invariances.